Xiao Zhang's Projects
A Toolbox for Adversarial Robustness Research
This is the Army Research Laboratory (ARL) EEGModels Project: A Collection of Convolutional Neural Network (CNN) models for EEG signal classification, using Keras and Tensorflow
This is a collection of CNNs trained on CIFAR10, e.g. DenseNet, VGG16, ResNet...
最简单的魔改发布『 合成大西瓜 』,配套改图工具,不用改代码,修改配置即可!
This is a toolbox to construct adversarial examples of EEG signals. The traditional EEG extraction methods and classifiers are re-implemented in Tensorflow.
An comparative study on the paper Exploring Generalization in Deep Learning https://papers.nips.cc/paper/7176-exploring-generalization-in-deep-learning.pdf
Computing various measures and generalization bounds on convolutional and fully connected networks
Deep Learning for humans
This project is aimed to provide a simple interface to attack the models built with Keras. It can be very simple to craft adversarial examples with different attacking methods using our API.
汇总各大互联网公司容易考察的高频leetcode题🔥
This project is mainly about Local Field Potential (LFP).
This repo aims to provide an easy-to-use interface for searching the lottery ticket of a DNN structure.
This repository is the official implementation of "Optimization Variance: Delve into the Epoch-Wise Double Descent of DNNs"
Pytorch implementation of convolutional neural network visualization techniques
A Collection of Variational Autoencoders (VAE) in PyTorch.
This is a PyTorch reimplementation of Influence Functions from the ICML2017 best paper: Understanding Black-box Predictions via Influence Functions by Pang Wei Koh and Percy Liang.
This is a respository which implements several recomender systems in Python.
This repository is the official implementation of "Rethink the Connections among Generalization, Memorization and Spectral Bias" https://arxiv.org/abs/2004.13954.
This project attacked widely-used EEG spellers, e.g., P300 spellers and SSVEP spellers, with adversarial perturbation templates. We constructed these templates to perform target attacks on EEG spellers, demonstrating that the spellers can be manipulated to output anything the attacker wants when added the templates.
This project is the codes to generate universal adversarial perturbations for EEG-based BCIs.
https://zhangxiao96.github.io/